Hugging Face
Search models, datasets, users...
Ctrl K
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
kurcontko
/
clef-NVFP4
Like
3
Safetensors
vllm
qwen3_5
clef
systemone
jev
nvfp4
compressed-tensors
llm-compressor
qwen3.8
structured-output
classification
8-bit precision
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
clef-NVFP4
/
scripts
Commit History
Oct 7
19:56
8-bit lookup tables: 20.0 -> 17.5 GB, same accuracy and speed; faster server (prompt-sized CUDA graphs, --gdn-backend)
kurcontko
Verified signature
1abd566
Oct 4
07:53
Upload clef-NVFP4 (Clef 27B NVFP4, vLLM plugin + SystemOne server)
kurcontko
Verified signature
6ba50d1